🤖 Reinforcement Learning - a1k0n · Scour

Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning

🤖AI Academic

Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation

🤖Robotics Academic

Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulation

🤖Robotics Academic

Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box Agents

🤖AI Academic

UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning

🤖AI Academic

Discovering Interpretable Multi-Parameter Control Policies for Evolutionary Algorithms Using Deep Reinforcement Learning

🤖Machine Learning Academic

APPO: Agentic Procedural Policy Optimization

🤖AI Academic

Representation Learning Enables Scalable Multitask Deep Reinforcement Learning

🤖AI Academic

Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible Action Sets

🤖Machine Learning Academic

CCKS: Consensus-based Communication and Knowledge Sharing

🤖Transformers Academic

Deep reinforcement learning for process design: Review and perspective

🤖Machine Learning Academic

PAWS: Preference Learning with Advantage-Weighted Segments

🤖Machine Learning Academic

Drag reduction or reward hacking? Recurrent multi-agent reinforcement learning that earns its reward

🤖Robotics Academic

Development of COVID-19 Booster Vaccine Policy by Microsimulation and Q-learning

🤖Machine Learning Academic

INFRAMIND: Infrastructure-Aware Multi-Agent Orchestration

👁️Attention Mechanisms Academic

SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration

👁️Attention Mechanisms Academic

Self-evolving LLM agents with in-distribution Optimization

⚙️JIT Compilation Academic

IAPO: Input Attribution-Aware Policy Optimization for Tool Use in Small Multimodal Agents

🤖AI Academic

Geometrically Averaged Hard Target Updates for Linear Q-Learning

🤖Machine Learning Academic

RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation

🤖Machine Learning Academic

Log in to enable infinite scrolling